A robust and hybrid deep-linguistic theory applied to large scale parsing

Abstract

Modern statistical parsers are robust and quite fast, but their output is relatively shallow when compared to formal grammar parsers. We suggest to extend statistical approaches to a more deep-linguistic analysis while at the same time
keeping the speed and low complexity of a statistical parser. The resulting parsing architecture suggested, implemented and evaluated here is highly robust and hybrid on a number of levels, combining statistical and rule-based approaches, constituency and dependency grammar, shallow and deep processing, full and nearfull parsing. With its parsing speed of about 300,000 words per hour and state-of-the-art performance the parser is reliable for a number of large-scale applications discussed in the article.